Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

Nicklas Hansen, Hao Su, Xiaolong Wang

Type: Preprint

Publication Date: 2021-01-01

Citations: 28

DOI: https://doi.org/10.48550/arxiv.2107.00644

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+ PDF Chat	A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning	2024	Abdulaziz Almuzairee Nicklas Hansen Henrik I. Christensen
+	Generalization in Reinforcement Learning by Soft Data Augmentation	2020	Nicklas Hansen Xiaolong Wang
+ PDF Chat	Don’t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning	2022	Zhecheng Yuan MA Guo-Zheng Yao Mu Bo Xia Bo Yuan Xueqian Wang Ping Luo Huazhe Xu
+	Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning	2022	Zhecheng Yuan Guozheng Ma Yao Mu Bo Xia Bo Yuan Xueqian Wang Ping Luo Huazhe Xu
+	Decoupling Representation Learning from Reinforcement Learning	2020	Adam Stooke Kimin Lee Pieter Abbeel Michael Laskin
+	Decoupling Representation Learning from Reinforcement Learning	2020	Adam Stooke Kimin Lee Pieter Abbeel Michael Laskin
+	Improving Sample Efficiency in Model-Free Reinforcement Learning from Images	2019	Denis Yarats Amy Zhang Ilya Kostrikov Brandon Amos Joëlle Pineau Rob Fergus
+ PDF Chat	Generalization in Reinforcement Learning by Soft Data Augmentation	2021	Nicklas Hansen Xiaolong Wang
+	A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning	2022	Guozheng Ma Zhen Wang Zhecheng Yuan Xueqian Wang Bo Yuan Dacheng Tao
+ PDF Chat	Zero-Shot Generalization of Vision-Based RL Without Data Augmentation	2024	Sumeet Batra Gaurav S. Sukhatme
+	Improving Sample Efficiency in Model-Free Reinforcement Learning from Images	2019	Denis Yarats Amy Zhang Ilya Kostrikov Brandon Amos Joëlle Pineau Rob Fergus
+ PDF Chat	Improving Sample Efficiency in Model-Free Reinforcement Learning from Images	2021	Denis Yarats Amy Zhang Ilya Kostrikov Brandon Amos Joëlle Pineau Rob Fergus
+ PDF Chat	EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data	2024	Shengjie Wang S.C. Liu Weirui Ye Jiacheng You Yang Gao
+	Stabilizing Off-Policy Deep Reinforcement Learning from Pixels	2022	Edoardo Cetin Philip Ball Steve Roberts Oya Çeliktutan
+	CoBERL: Contrastive BERT for Reinforcement Learning	2021	Andrea Banino Adrià Puidomenech Badia Jacob Walker Tim Scholtes Jovana Mitrovic Charles Blundell
+	CoBERL: Contrastive BERT for Reinforcement Learning	2021	Andrea Banino Adrià Puidomenech Badia Jacob Walker Tim Scholtes Jovana Mitrovic Charles Blundell
+	Pretraining Representations for Data-Efficient Reinforcement Learning	2021	Max Schwarzer Nitarshan Rajkumar Michael Noukhovitch Ankesh Anand Laurent Charlin R Devon Hjelm Philip Bachman Aaron Courville
+	Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning	2023	Guozheng Ma Linrui Zhang Haoyu Wang Lu Li Zilin Wang Zhen Wang Li Shen Xueqian Wang Dacheng Tao
+	Reinforcement Learning with Augmented Data	2020	Michael Laskin Kimin Lee Adam Stooke Lerrel Pinto Pieter Abbeel Aravind Srinivas
+	Pretraining Representations for Data-Efficient Reinforcement Learning	2021	Max Schwarzer Nitarshan Rajkumar Michael Noukhovitch Ankesh Anand Laurent Charlin Devon Hjelm Philip Bachman Aaron Courville

Works That Cite This (13)

Action	Title	Year	Authors
+ PDF Chat	Hierarchical Decision Transformer	2023	André Correia Luı́s A. Alexandre
+	Invariance Through Latent Alignment	2022	Takuma Yoneda Ge Yang Matthew R. Walter Bradly C. Stadie
+ PDF Chat	Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation	2024	Annie Xie Lisa Lee Ted Xiao Chelsea Finn
+	Look Closer: Bridging Egocentric and Third-Person Views With Transformers for Robotic Manipulation	2022	Rishabh Jangir Nicklas Hansen Sambaran Ghosal Mohit Jain Xiaolong Wang
+ PDF Chat	A Survey of Zero-shot Generalisation in Deep Reinforcement Learning	2023	Robert Kirk Amy Zhang Edward Grefenstette Tim Rocktäschel
+ PDF Chat	A Survey of Demonstration Learning	2023	André Correia Luı́s A. Alexandre
+ PDF Chat	Don’t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning	2022	Zhecheng Yuan MA Guo-Zheng Yao Mu Bo Xia Bo Yuan Xueqian Wang Ping Luo Huazhe Xu
+ PDF Chat	Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions	2023	Qiyuan Liu Qi Zhou Rui Yang Jie Wang
+ PDF Chat	Point Cloud Models Improve Visual Robustness in Robotic Learners	2024	Skand Vishwanath Peri Iain Lee Chanho Kim Fuxin Li Tucker Hermans Stefan Lee
+	Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization	2021	Chieko Sarah Imai Minghao Zhang Yuchen Zhang Marcin Kierebiński Ruihan Yang Yuzhe Qin Xiaolong Wang

Works Cited by This (43)

Action	Title	Year	Authors
+ PDF Chat	A Markovian Decision Process	1957	Richard Bellman
+	Deep reinforcement learning with double Q-Learning	2016	Hado van Hasselt Arthur Guez David Silver
+ PDF Chat	Deep Residual Learning for Image Recognition	2016	Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun
+ PDF Chat	Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours	2016	Lerrel Pinto Abhinav Gupta
+ PDF Chat	Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles	2016	Mehdi Noroozi Paolo Favaro
+ PDF Chat	Domain randomization for transferring deep neural networks from simulation to the real world	2017	Josh Tobin Rachel Fong Alex Ray Jonas Schneider Wojciech Zaremba Pieter Abbeel
+	Asymmetric Actor Critic for Image-Based Robot Learning	2017	Lerrel Pinto Marcin Andrychowicz Peter Welinder Wojciech Zaremba Pieter Abbeel
+	DeepMind Control Suite	2018	Yuval Tassa Yotam Doron Alistair Muldal Tom Erez Yazhe Li Diego de Las Casas David Budden Abbas Abdolmaleki Josh Merel Andrew Lefrancq
+	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor	2018	Tuomas Haarnoja Aurick Zhou Pieter Abbeel Sergey Levine
+	Addressing Function Approximation Error in Actor-Critic Methods	2018	Scott Fujimoto Herke van Hoof David Meger